Brain-computer interface system utilizing visually evoked potentials for communication and cognitive rehabilitation and method thereof
Patent Information
- Application Number
- IN202421105278
- Authority / Receiving Office
- IN · IN
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-12-31
- Publication Date
- 2026-07-09
- Estimated Expiration
- 2044-12-31
AI Technical Summary
Existing Brain-Computer Interface (BCI) systems utilizing Visually Evoked Potentials (VEPs) face challenges such as high latency, limited adaptability, and lack of user-friendly interfaces, which hinder their effectiveness in everyday communication and therapeutic use for individuals with severe motor impairments.
A dual-functional BCI system that integrates gaze-controlled communication and adaptive visual stimulation programs, utilizing VEP detection for precise interaction and cognitive rehabilitation, with real-time feedback and modular design for compatibility with various EEG devices and display technologies.
The system enables effective communication and cognitive rehabilitation for individuals with severe motor impairments by providing intuitive, adaptable, and comprehensive solutions that enhance visual processing and attention, with real-time feedback and detailed performance monitoring.
Abstract
Description
TECHNICAL FIELDThe present invention relates to Brain-Computer Interface (BCI) systems, particularly those utilizing Visually Evoked Potentials (VEPs) to enable communication and enhance cognitive abilities. This invention addresses the needs of individuals with severe motor impairments by providing non-invasive tools for communication and neural rehabilitation.BACKGROUNDIndividuals with severe motor impairments face significant challenges in interacting with their environment and effectively communicating their needs. Conventional assistive technologies, such as manual input devices or speech-based systems, often fail to meet the specific requirements of these users due to their reliance on physical or vocal capabilities. The lack of intuitive design, coupled with limitations in accuracy and adaptability, underscores the need for innovative solutions tailored to this population. Effective communication is a fundamental challenge for individuals with severe motor impairments, as traditional interaction methods often fail to accommodate their needs. Existing assistive technologies, such as manual input devices or voice recognition systems, are frequently inadequate due to physical limitations or situational constraints.Emerging brain-computer interface (BCI) technologies offer a promising alternative, particularly those leveraging non-invasive electroencephalogram (EEG) signals. Visually Evoked Potentials (VEPs), derived from EEG data, provide a unique method to decode user intent based on brain responses to visual stimuli. Brain-computer interfaces, particularly those leveraging Visually Evoked Potentials (VEPs) derived from electroencephalogram (EEG) signals, have shown promise in providing non-invasive communication solutions. VEPs are specific brain responses triggered by visual stimuli, which can be detected and processed in real time to decode user intent. However, existing systems often struggle to combine real-time functionality, user-friendly interfaces, and personalized adaptability, limiting their effectiveness in everyday communication or therapeutic use. Further, existing systems employing VEPs have demonstrated potential, they often suffer from challenges such as high latency, limited adaptability, and lack of user-friendly interfaces. These limitations hinder their usability and effectiveness, particularly in therapeutic or everyday communication scenarios. Despite the promise of BCIs, most current systems are either overly complex or narrowly focused on a single application, such as communication. This narrow focus limits their therapeutic potential and fails to address the holistic needs of individuals with severe impairments. Furthermore, the integration of real-time feedback and progress tracking remains an underdeveloped aspect in existing solutions. Thus, there is a need for a technical solution that overcomes the aforementioned problems of conventional fake news prediction techniques.SUMMARYThe present disclosure relates generally to techniques of improving vision. More particularly, the present disclosure relates to brain-computer interface (BCI) system utilizing visually evoked potentials (VEPs) for communication and cognitive rehabilitation and method thereof. The present invention relates to Brain-Computer Interface (BCI) technologies, specifically designed for individuals with severe motor impairments. The invention utilizes Visually Evoked Potentials (VEPs) to provide a non-invasive means for communication and cognitive rehabilitation. The system combines advanced neural detection techniques with user-centric designs to enhance accessibility and therapeutic efficacy.Brain-Computer Interfaces have emerged as a groundbreaking technology for enabling direct communication between the brain and external devices. VEPs, a subset of neural responses, are especially valuable in this domain due to their high signal reliability and response accuracy to visual stimuli. This invention builds upon the potential of VEPs by integrating them into a comprehensive system that supports both communication and cognitive enhancement.The application focuses on addressing the limitations of existing assistive technologies. Traditional methods like switch-based systems or eye-tracking devices often fail to meet the nuanced needs of users with severe impairments. This invention overcomes these limitations through precision-based VEP detection and adaptive neural stimulation programs.The invention’s dual-functional design also extends its utility beyond communication to visual and cognitive rehabilitation. Tailored exercises adapt dynamically to user responses, fostering long-term improvements in visual processing and attention. This dual capability distinguishes the invention in the field of assistive technologies.Finally, the modular nature of the system ensures compatibility with various EEG devices and display screens, making it adaptable to diverse clinical and home-care environments. Its user-friendly interfaces for patients and therapists further enhance its accessibility and usability.This invention bridges these gaps by integrating VEP detection into a dual-functional system. By combining a gaze-controlled communication device with a visual stimulation program, it provides a comprehensive solution for both interaction and rehabilitation. The system's ability to adapt exercises based on user performance further enhances its therapeutic value.Another critical aspect addressed by this invention is accessibility. By ensuring compatibility with commercial EEG headsets and various display technologies, the system reduces barriers to adoption. Its modular design also facilitates future upgrades, allowing the integration of additional functionalities as needed.Finally, the inclusion of real-time feedback mechanisms ensures that users receive immediate reinforcement of their actions, enhancing both motivation and accuracy. This feedback system, combined with detailed performance monitoring, makes the invention a robust tool for both users and therapists.The invention comprises a dual-functional Brain-Computer Interface (BCI) system designed to utilize Visually Evoked Potentials (VEPs) for communication and cognitive rehabilitation. It addresses the needs of individuals with severe motor impairments by providing a gaze-controlled communication device and an adaptive visual stimulation program.The gaze-controlled communication device allows users to interact with on-screen elements by focusing their gaze on specific visual stimuli. VEPs triggered by these stimuli are detected and classified, enabling precise selections of letters, words, or phrases. This feature empowers users to communicate effectively without requiring physical input.The visual stimulation program is equally significant, offering tailored exercises that adapt to the user's cognitive abilities. These exercises aim to enhance visual processing and attention, leveraging the user’s neural responses to ensure effectiveness. The program gradually increases in complexity, fostering sustained cognitive improvement.A unique feature of the system is its real-time feedback mechanism. Users receive immediate visual, auditory, or tactile cues based on their selections and performance. This feedback not only reinforces user actions but also maintains motivation and engagement throughout the session.The invention also includes a comprehensive performance monitoring module. This module logs EEG data, VEP detection rates, and user interactions, providing detailed analytics for therapists. The data aids in customizing therapy sessions and measuring progress over time.Lastly, the modular design of the system ensures compatibility with a wide range of EEG devices and display technologies. This adaptability makes the system suitable for various clinical, home-care, and rehabilitation settings, expanding its applicability across diverse user groups.BRIEF DESCRIPTION OF DRAWINGSThe above and still further features and advantages of aspects of the present disclosure becomes apparent upon consideration of the following detailed description of aspects thereof, especially when taken in conjunction with the accompanying drawings, and wherein:FIG. 1 illustrates a block diagram of a gaze communication system, in accordance with an embodiment of the present disclosure; FIG. 2 illustrates a flowchart of a method for facilitating gaze communication with a user, in accordance with an embodiment of the present disclosure; and FIG. 3 illustrates an example-computing environment implementing the system as shown in FIG. 1, in accordance with an embodiment of the present disclosure. DETAILED DESCRIPTIONEmbodiments of the present invention discloses a dual-functional brain-computer interface (BCI) system designed to utilize visually evoked potentials (VEPs) for communication and cognitive rehabilitation. It addresses the needs of individuals with severe motor impairments by providing a gaze-controlled communication device and an adaptive visual stimulation program.The gaze-controlled communication device allows users to interact with on-screen elements by focusing their gaze on specific visual stimuli. VEPs triggered by these stimuli are detected and classified, enabling precise selections of letters, words, or phrases. This feature empowers users to communicate effectively without requiring physical input.The visual stimulation program is equally significant, offering tailored exercises that adapt to the user's cognitive abilities. These exercises aim to enhance visual processing and attention, leveraging the user’s neural responses to ensure effectiveness. The program gradually increases in complexity, fostering sustained cognitive improvement.A unique feature of the system is its real-time feedback mechanism. Users receive immediate visual, auditory, or tactile cues based on their selections and performance. This feedback not only reinforces user actions but also maintains motivation and engagement throughout the session.The invention also includes a comprehensive performance monitoring module. This module logs EEG data, VEP detection rates, and user interactions, providing detailed analytics for therapists. The data aids in customizing therapy sessions and measuring progress over time.Lastly, the modular design of the system ensures compatibility with a wide range of EEG devices and display technologies. This adaptability makes the system suitable for various clinical, home-care, and rehabilitation settings, expanding its applicability across diverse user groups.The proposed system integrates hardware and software modules to enable seamless interaction and rehabilitation through VEP detection. The architecture comprises an EEG signal acquisition unit, a signal processing and classification module, a gaze-controlled communication interface, and a visual stimulation program.EEG signal acquisition is facilitated through non-invasive headsets that capture neural activity in response to visual stimuli. These signals are processed to isolate VEP features such as P100, N75, and N145 components. Advanced algorithms classify these features to identify user intent.The gaze-controlled communication interface allows users to select on-screen options, such as letters or words, by focusing their gaze. The system’s design ensures intuitive interaction, requiring minimal training for users.The visual stimulation program complements the communication module by offering tailored exercises. These exercises dynamically adjust to the user's performance, targeting specific cognitive skills like attention and processing speed.Finally, the system includes robust data logging and analytics capabilities. All interactions and EEG data are recorded, enabling therapists to track progress and refine therapy strategies.VEP detection is the cornerstone of the system. It begins with EEG signal acquisition using a non-invasive headset. These signals are then filtered to remove noise and artifacts, ensuring high-quality data for analysis.The next step involves feature extraction, where specific VEP characteristics are identified. Machine learning algorithms classify these features to detect user intent accurately. This classification drives both communication selections and exercise adjustments.Continuous monitoring ensures that VEP responses are reliably detected throughout each session. This real-time capability is crucial for maintaining the system's responsiveness and accuracy.Accordingly, embodiments of the present invention provides abrain-computer interface (BCI) system and method utilizing visually evoked potentials (VEPs) is disclosed. The system includes a gaze-controlled communication device and a visual stimulation program for individuals with severe motor impairments. The invention leverages real-time VEP detection for communication and tailored exercises to enhance cognitive functions. Key features include non-invasive EEG acquisition, adaptive feedback, and detailed performance analytics, ensuring effective rehabilitation and communication.FIG. 1 illustrates a block diagram of a gaze communication system 100, in accordance with an embodiment of the present disclosure. The gaze communication system 100 (hereinafter referred to and designated as “the system 100”) may be configured to improve vision of a user. The system 100 may be configured to provide various exercises to the user that may improve the vision of the user. The system 100 may include a sensing unit 102, a processor 104, a user interface 106, and a feedback unit 108. The sensing unit 102 may be configured to sense a plurality of electroencephalogram (EEG) signals associated with a user. The processor 104 may be coupled to the sensing unit 102. The processor 104 may be configured to filter the EEG signals to remove noise and artifacts from EEG data associated with the EEG signals. The processor 104 may be further configured to extract a plurality of features associated with Visually Evoked Potentials (VEP) of the user. The processor 104 may be further configured to identify VEP corresponding to at least one visual stimuli associated with the user. The VEP corresponding to the at least one visual stimuli is identified by way of classification of the plurality of features. The user interface 106 may be coupled to the processor 104. The user interface 106 may be configured to display visual information such that the user performs the visual stimuli in response to the visual information. The user performs the visual stimuli. The visual information comprising one of, letters, words, and phrases. The user, to facilitate gaze communication, selects at least one attribute of the visual information. In some embodiments of the present disclosure, the plurality of features comprising one of, a P100, N75, and N145 components. The processor 104 may be further configured to trigger a selection mechanism when the at least one visual stimulus is identified. The processor 104 may be configured to generate a prediction signal that facilitates to suggest the visual information to the user. The processor 104, upon selection of the at least one attribute of the visual information by the user, generates a feedback signal.The feedback unit 108 may be coupled to the processor 104. The feedback unit 108 may be configured to generate one of, a visual feedback, a haptic feedback, and an audio feedback upon generation of the feedback signal. The system 100 integrates several essential components designed to deliver efficient gaze-based communication and cognitive enhancement. The EEG Signal Acquisition Unit is a non-invasive device that captures EEG signals while users interact with visual stimuli. These signals are processed in a Signal Processing Module, which filters out noise and extracts key features associated with Visually Evoked Potentials (VEPs), such as P100, N75, and N145. A Gaze-Controlled Interface provides a user-friendly graphical platform for selecting letters, words, or phrases by focusing on specific visual stimuli. To support cognitive improvements, system 100 includes a Visual Stimulation Program offering exercises that adapt dynamically based on user responses. Lastly, a Feedback Mechanism delivers real-time visual, auditory, or tactile cues to confirm selections or guide users during exercises. The functionality of the system 100 centres on detecting and classifying VEPs to facilitate seamless user interaction. EEG signals, captured through a non-invasive headset, undergo preprocessing to filter noise and artifacts. Key VEP-related features are extracted and classified in real-time to identify responses to visual stimuli. This allows the system 100 to enable Gaze-Based Communication, where users interact with on-screen content, selecting visual elements by focusing on them. Upon detecting a VEP signal, the system 100 triggers a selection mechanism, while integrated word prediction algorithms enhance efficiency by suggesting likely word completions. To improve visual processing, the system 100 includes a Visual Stimulation Program that adapts exercises dynamically based on real-time VEP feedback. These exercises, progressively increasing in complexity, target the user's focus and attention capabilities. Immediate and Real-Time Feedback is essential to the user experience, with cues provided through visual highlights, auditory tones, or tactile vibrations. This feedback not only confirms actions but also helps guide users through the communication process or visual exercises. The system 100 includes robust Performance Monitoring features to track user progress. It records metrics such as VEP detection accuracy and communication efficiency, providing detailed analytics and session reports. These insights are invaluable for therapists and users, allowing for personalized adjustments to therapy or training sessions. Detailed performance data supports both therapeutic decision-making and user motivation, enhancing the overall impact of system 100. The system 100 comprising an EEG acquisition unit, a signal processing module for filtering and classifying VEPs, a gaze-controlled graphical user interface, and a feedback mechanism. Visual stimuli may include letters, words, or phrases to support communication, and feedback is offered through multimodal outputs such as visual, auditory, and tactile cues. Key advantages of the system 100 include a Non-Invasive Design, real-time processing, tailored visual stimulation for cognitive enhancement, multi-modal feedback, and comprehensive data analytics for therapeutic applications. Preferred embodiments of the system 100 feature a lightweight, wireless EEG headset for seamless integration with the processing module. The user interface offers high-contrast, customizable layouts, catering to individuals with visual or cognitive impairments. Exercises involve engaging tasks such as identifying moving patterns or dynamic stimuli, gradually increasing in difficulty as users improve. Optional illustrations, including the system Architecture Diagram, Data Flow Diagram, and User Interfaces, depict the EEG signal acquisition, data processing pipeline, and user interaction for enhanced understanding and visualization of the system 100. In another embodiment, gaze communication system (100) for utilizing visually evoked potentials (VEPs) of a user for communication and cognitive rehabilitation is provided. In a preferred embodiment, the system includesa sensing unit (102), a processor (104), a user interface (106), and a gaze-controlled communication device (110).Sensing Unit (102): The system incorporates a sensing unit capable of capturing electroencephalogram (EEG) signals associated with the user's brain activity. These signals serve as the foundation for identifying VEPs, which are neural responses triggered by visual stimuli.Processor (104): A powerful processor is coupled to the sensing unit. It performs essential signal processing tasks through a dedicated module. The raw EEG data, prone to noise and artifacts, is filtered and pre-processed to isolate clean signals suitable for analysis. This ensures the accuracy and reliability of subsequent steps.Feature Extraction: The processor extracts key features from the cleaned EEG signals. These features, such as P100, N75, and N145 components, are strongly associated with VEPs and are crucial for identifying user responses to visual stimuli.Classification and Identification: The system uses machine learning techniques to classify the extracted features. This step allows for precise identification of VEPs corresponding to specific visual stimuli displayed on the user interface. This ensures real-time detection of the user’s gaze focus and intent.Feedback via Gaze-Controlled Communication Device (110): The system provides real-time feedback to the user through a gaze-controlled device. This feedback can recommend selections such as letters, words, or phrases displayed on a user interface (106). By focusing on a visual stimulus, the user can engage in effective communication facilitated by the system.The sensing unit (102) can integrate a variety of EEG devices to capture neural signals. Examples include popular and advanced systems like EmotivEpoc+, OpenBCI EEG Systems, Muse 2, and Muse S. Additionally, integrated multi-bio-signal systems, such as Empatica E4 and Shimmer3, offer enhanced capabilities by combining EEG data with other physiological signals.These technologies improve the system's adaptability and precision. By allowing compatibility with multiple hardware options, the system ensures accessibility and ease of integration across different environments and user needs.The user interface (106) is a central component that bridges the user and the system. It displays visual information, including letters, words, and phrases, which the user interacts with through gaze focus.Generation of Visual Stimulus: When the user views the visual content, the system captures their neural response as a VEP, triggered by the displayed stimulus. The interface is designed to elicit clear and measurable neural signals, making it highly effective for gaze communication.Facilitating Gaze Communication: Users can select specific attributes of the displayed visual information by focusing their gaze. This interaction is seamless and intuitive, empowering individuals with limited motor abilities to communicate effectively.Feature Components for VEP Identification:The system’s feature extraction process identifies distinct VEP components such as P100, N75, and N145. These components are well-documented in neuroscience as critical markers of visual processing in the brain.P100 Component: Known for its robust and consistent response, this component represents early visual processing.N75 Component: This component reflects initial neural activity upon exposure to visual stimuli.N145 Component: Occurring later in the visual processing chain, this component provides additional granularity to the user’s neural response.Machine Learning for VEP Classification:The classification of VEPs is facilitated by advanced machine learning techniques. These algorithms analyze patterns within the extracted features to accurately map them to corresponding visual stimuli.Machine learning models are trained using extensive datasets, ensuring they adapt to individual user variations and environmental conditions. This adaptability enhances the system's robustness and accuracy, making it reliable across diverse use cases.Prediction for Enhanced User Interaction:The processor (104) generates prediction signals that enhance the system’s communication efficiency. For instance, based on the user’s previous selections or gaze patterns, the system suggests likely visual information.This predictive feature minimizes effort and reduces cognitive load for the user, particularly beneficial for individuals with severe impairments. It enables faster communication by streamlining the selection process.Selection Mechanism and Feedback Generation:The gaze-controlled communication device includes a selection mechanism that is triggered upon identifying VEPs corresponding to specific visual stimuli.Recommendation-Based Interaction: The system provides recommendations to the user, such as specific letters, words, or phrases, based on their gaze focus. Upon selection, the system generates a feedback signal to confirm the user’s choice.This mechanism ensures accuracy and reinforces user actions, creating a fluid interaction loop that is critical for effective communication.Feedback Unit for Multimodal Responses:The feedback unit (108) enhances user experience by offering visual, haptic, or auditory feedback.Visual Feedback: Highlighting selected options on the screen to confirm user actions.Haptic Feedback: Delivering vibrations through wearable devices to provide tactile confirmation.Auditory Feedback: Playing audio prompts or confirmations for accessibility, especially for users with visual impairments.This multimodal feedback mechanism ensures the system caters to a wide range of user preferences and needs, making it universally accessible and effective.The gaze communication system described in the claims can be implemented using advanced sensing, signal processing, machine learning, and feedback technologies.Sensing Unit and EEG Signal Acquisition: The system employs an EEG sensing unit capable of capturing brain activity with high precision. Devices such as the EmotivEpoc+ or OpenBCI EEG Systems are ideal for this purpose. These devices use non-invasive electrodes to record EEG signals from the user's scalp. Signal acquisition software processes these recordings in real time to ensure the data is suitable for downstream analysis. To ensure signal quality, these systems can implement real-time impedance checks and adaptive noise suppression techniques, reducing interference from muscle movements or environmental noise.Signal Pre-Processing and Feature Extraction: Once the EEG signals are captured, they are filtered and pre-processed to remove noise and artifacts. Techniques such as band-pass filtering (e.g., 1-50 Hz) and Independent Component Analysis (ICA) are employed to isolate the neural signals corresponding to visual stimuli. This step ensures that only the most relevant EEG data is analyzed further.The processed signals are then passed through a feature extraction algorithm. The system specifically identifies the P100, N75, and N145 components, which are distinct markers of visually evoked potentials (VEPs). Time-domain analysis can be used to locate these components, while wavelet transforms or Fourier transforms may extract additional frequency-domain features. These extracted features are crucial for distinguishing the user's response to visual stimuli.Classification of Visually Evoked Potentials: Machine learning techniques play a pivotal role in classifying the extracted VEP features. Algorithms such as Support Vector Machines (SVM), Random Forests, or Convolutional Neural Networks (CNNs) are trained on labeled datasets containing EEG recordings corresponding to known visual stimuli. For instance, if the system uses CNNs, it processes the extracted features as input vectors, allowing the model to identify the VEP patterns with high accuracy.Real-time classification is achieved using lightweight implementations of these algorithms, optimized for execution on edge devices or processors integrated within the system. By associating specific VEP patterns with the visual stimuli displayed on the user interface, the system can reliably interpret the user’s intent.Gaze-Controlled Communication Interface and User Interaction: The system features an intuitive gaze-controlled interface. This interface, displayed on a tablet or monitor, presents letters, words, or phrases as selectable options. Visual stimuli are dynamically updated based on user progress and preferences. Algorithms like saliency mapping can enhance visual elements, ensuring they effectively capture the user’s gaze.When a user focuses on a specific visual stimulus, the system detects and classifies the associated VEP. A selection mechanism is triggered, and the system provides a recommendation, such as predicting the user’s next word or phrase based on their previous selections. Predictive text algorithms, similar to those used in smartphones, are integrated into this process, significantly improving the speed of communication.Feedback Mechanism and Multimodal Reinforcement: The system’s feedback unit delivers real-time responses to the user. For instance, when the system detects and confirms a selection, it visually highlights the chosen letter or phrase on the screen. Simultaneously, auditory feedback, such as a confirmation beep, is played to reinforce the action. For users requiring additional confirmation, haptic feedback is delivered through wearable devices like smartwatches or vibration modules.The feedback loop employs algorithms to adaptively adjust the feedback intensity based on user preferences and performance. For example, reinforcement learning algorithms can fine-tune the feedback over time, ensuring it remains engaging and non-intrusive.Performance Monitoring and Analytics:To track user progress and system effectiveness, the system includes a robust data logging and analytics module. EEG data, VEP classification results, and user interactions are recorded during each session. Analytics tools use time-series analysis and statistical models to identify trends in user performance, such as improved accuracy in gaze selections or reduced response times.These insights are visualized on a therapist dashboard, enabling healthcare providers to customize therapy sessions based on the user’s needs. The system can also employ predictive analytics to forecast user performance, assisting therapists in planning long-term rehabilitation strategies.Integration of Advanced Prediction and Selection Mechanisms: The processor generates prediction signals to assist users in their interactions. For instance, if a user frequently selects certain words, the system prioritizes those options using algorithms such as Markov chains or recurrent neural networks (RNNs). These algorithms learn from user patterns, providing personalized suggestions that minimize cognitive load.Upon detecting a VEP corresponding to a particular visual stimulus, the gaze-controlled device triggers a selection mechanism. This mechanism relies on real-time decision trees to confirm the user's intent and execute the corresponding action. Feedback is generated based on this action, closing the interaction loop effectively.System Scalability and Adaptability: The system is designed to be hardware-agnostic, supporting a wide range of EEG devices and display technologies. For example, it can integrate with virtual reality (VR) headsets for immersive therapy sessions or standard monitors for conventional rehabilitation setups. Its modular software architecture supports API integrations, allowing compatibility with telehealth platforms or other assistive technologies.In conclusion, the implementation of this gaze communication system leverages cutting-edge techniques in sensing, signal processing, machine learning, and feedback delivery to provide a robust, adaptive, and user-friendly solution. This real-world approach ensures the system meets diverse user needs, making it a versatile tool for communication and cognitive rehabilitation.In an exemplary embodiment, each of the gaze communication system (100), or a sensing unit (102), ora processor (104), or a gaze-controlled communication device (110), ora user interface (106) can be implemented in the form of computing devices. In an exemplary implementation, the one or more computing devices may include, but not be limited to, any electrical, electronic, electro-mechanical, or an equipment, or a combination of one or more of the above devices such as mobile phone, smartphone, Virtual Reality (VR) devices, Augmented Reality (AR) devices, laptop, a general-purpose computer, desktop, personal digital assistant, tablet computer, mainframe computer, or any other computing device, wherein the one or more computing devices may include one or more in-built or externally coupled accessories including, but not limited to, a visual aid device such as camera, audio aid, a microphone, a keyboard, input devices such as touch pad, touch enabled screen, electronic pen, receiving devices for receiving any audio or visual signal in any range of frequencies, and transmitting devices that can transmit any audio or visual signal in any range of frequencies. It may be appreciated that the one or more computing devices may not be restricted to the mentioned devices and various other devices may be used.In an exemplary embodiment, each of the gaze communication system (100), or a sensing unit (102), ora processor (104), or a gaze-controlled communication device (110), ora user interface (106) can be connected to each other through a network, and may include but not limited to personal computers, smartphones, laptops, tablets, smart watches as well as other IoT devices that support a display. The network may be further configured with a centralized server including a database, where all output is stored as part of medical records of the patient. It can be retrieved whenever there is a need to reference this output in future.FIG. 2 illustrates a flowchart of a method 200 for facilitating gaze communication with the user. The method 200 may include various steps for facilitating gaze communication with the user. At step 202, the method 200 may include a step of sensing, by way of the sensing unit 102, the plurality of electroencephalogram (EEG) signals associated with a user. At step 204, the method 200 may include a step of filtering, by way of the processor 104 coupled to the sensing unit 102, the EEG signals to remove noise and artifacts from EEG data associated with the EEG signals. At step 206, the method 200 may include a step of extracting, by way of the processor 104, the plurality of features associated with Visually Evoked Potentials (VEP) of the user. At step 208, the method 200 may include a step of identifying, by way of the processor 104, VEP corresponding to at least one visual stimuli associated with the user. The VEP corresponding to the at least one visual stimuli is identified by way of classification of the plurality of features. At step 210, the method 200 may include a step of displaying, by way of the user interface 106 coupled to the processor 104, visual information such that the user performs the visual stimuli in response to the visual information. The user performs the visual stimuli. The visual information comprising one of, letters, words, and phrases. The user, to facilitate gaze communication, selects at least one attribute of the visual information. The processor 104, upon selection of the at least one attribute of the visual information by the user, generates a feedback signal.At step 212, the method 200 may include a step of generating, by way of a feedback unit 108 coupled to the processor 104, one of, a visual feedback, a haptic feedback, and an audio feedback upon generation of the feedback signal. To summarize, the method (200) outlines a systematic approach for using visually evoked potentials (VEPs) to facilitate communication and cognitive rehabilitation. The process begins with sensing (202) electroencephalogram (EEG) signals using advanced EEG sensors such as EmotivEpoc+, OpenBCI EEG Systems, or Muse devices. These non-invasive sensors capture neural activity generated in response to visual stimuli presented to the user. Integrated multi-bio-signal systems like Empatica E4 or Shimmer3 can also enhance signal acquisition by combining EEG data with additional physiological parameters for improved accuracy.After acquiring the EEG signals, the processor (104) initiates filtering and pre-processing (204). This step involves removing noise and artifacts from the raw EEG data using advanced signal processing techniques, such as band-pass filtering or Independent Component Analysis (ICA). The clean data is then subjected to feature extraction (206), focusing on identifying key VEP components like P100, N75, and N145. These components are essential markers of the user’s neural response to visual stimuli and are extracted using time-domain and frequency-domain analysis.The extracted features are subsequently classified and identified (208) by the processor using machine learning algorithms such as Support Vector Machines (SVM) or Convolutional Neural Networks (CNNs). This classification associates specific VEPs with visual stimuli displayed on the user interface (106). Once VEPs are identified, the gaze-controlled communication device (110) provides real-time feedback (210) to the user. This feedback includes recommendations for selecting letters, words, or phrases displayed on the user interface. The selection mechanism is triggered upon detecting the relevant VEPs, and the system generates a feedback signal confirming the user’s choice, enabling seamless interaction.The method further provides additional functionalities to enhance the user’s interaction with the system. The user interface (106) displays visual information, such as letters, words, or phrases, prompting the user to generate a visual stimulus in response. For example, focusing on a specific letter triggers the sensing of VEPs, which are processed to identify the user’s intent. The interface design ensures clarity and accessibility, facilitating effortless gaze communication.To improve efficiency, the method includes generating a prediction signal based on user behaviour. For instance, if a user frequently selects specific words, predictive algorithms such as recurrent neural networks (RNNs) suggest probable next words or phrases. This predictive capability reduces cognitive effort and accelerates communication, making the system highly adaptive to individual user patterns.Upon generating a feedback signal, the system provides multimodal feedback to confirm user actions. This feedback can be visual (highlighting the selected option), haptic (vibrations through a wearable device), or auditory (spoken confirmation). These feedback mechanisms not only enhance user confidence but also make the system inclusive for individuals with varying sensory abilities. The integration of these features ensures a robust, intuitive, and efficient interaction process, advancing both communication and cognitive rehabilitation.From implementation perspective, following techniques can be used to implement the invention:Sensing EEG Signals (202): To sense EEG signals associated with visually evoked potentials (VEPs), advanced non-invasive devices like EmotivEpoc+, OpenBCI EEG Systems, Muse 2, or Muse S can be utilized. These devices use dry or semi-dry electrodes for high-quality signal acquisition, reducing the need for extensive preparation while maintaining reliable contact with the scalp. For more comprehensive analysis, integrated multi-bio-signal systems like Empatica E4 or Shimmer3 can complement EEG data with physiological measurements such as heart rate variability or skin conductance, providing additional insights into the user's state during the session.These systems are often paired with proprietary software development kits (SDKs) or APIs that allow real-time data acquisition and synchronization. Techniques like real-time impedance monitoring ensure the electrodes maintain optimal contact, while dynamic sampling rate adjustments (e.g., 128 Hz to 256 Hz) enable high-resolution capture of neural signals for precise VEP detection.Filtering and Pre-Processing (204): The EEG signals acquired are pre-processed to remove noise and artifacts caused by muscle movements, electrical interference, or other external factors. Signal processing modules use techniques such as band-pass filtering to isolate frequencies within the 1–50 Hz range, where VEP components typically occur. Adaptive noise cancellation methods can be applied to further enhance signal quality, dynamically suppressing interference without distorting relevant neural activity.Independent Component Analysis (ICA) or Principal Component Analysis (PCA) is used to separate and identify noise sources, such as eye blinks or muscle artifacts, which are then excluded from the dataset. Additionally, techniques like wavelet denoising are employed to preserve the temporal characteristics of the VEP signals while eliminating high-frequency noise.Feature Extraction (206): Feature extraction focuses on identifying critical components of VEPs, such as P100, N75, and N145, which are indicative of the user's neural response to visual stimuli. These components are extracted using time-domain analysis, where peak latencies and amplitudes are measured directly from the EEG signal. Frequency-domain techniques, such as Short-Time Fourier Transform (STFT) or wavelet transform, are used to analyze oscillatory patterns associated with VEPs. These techniques provide insights into how neural responses evolve over time, crucial for distinguishing between different types of stimuli. In some cases, advanced approaches like Empirical Mode Decomposition (EMD) are utilized to decompose complex signals into intrinsic mode functions, isolating features that may not be apparent using traditional methods.Classification and Identification of VEPs (208): Machine learning algorithms play a vital role in classifying and identifying VEPs. Supervised learning techniques, such as Support Vector Machines (SVM) or Random Forests, are commonly employed to map the extracted features to specific visual stimuli. These models are trained on datasets containing labeled EEG recordings, allowing them to learn patterns associated with different VEP responses.For more dynamic and adaptable systems, Convolutional Neural Networks (CNNs) are used. CNNs process the extracted EEG features as input vectors, enabling high-accuracy classification by identifying intricate patterns in the data. Additionally, Recurrent Neural Networks (RNNs), particularly those utilizing Long Short-Term Memory (LSTM) units, are employed to account for the temporal dependencies in EEG signals, ensuring reliable classification even under varying conditions.Providing Real-Time Feedback (210): Once VEPs are identified, the system provides real-time feedback to the user through a gaze-controlled communication device. The processor generates recommendations based on the detected VEPs, such as selecting specific letters, words, or phrases displayed on a user interface. Predictive algorithms like Markov Chains or recurrent neural networks (RNNs) enhance this process by anticipating the user's next selection based on their interaction history, improving the speed and efficiency of communication.The feedback loop employs multimodal responses to confirm the user’s actions. For instance, visual feedback highlights the selected option on the screen, while auditory feedback provides a confirmation tone. Tactile feedback, such as gentle vibrations, can also be delivered via wearable devices, ensuring inclusivity for users with varying sensory preferences. Real-time feedback ensures a seamless user experience, allowing for continuous and intuitive interaction.This integration of advanced techniques and algorithms enables a robust, adaptive, and user-friendly implementation of the described method for utilizing VEPs in communication and cognitive rehabilitation.FIG. 3 illustrates an example-computing environment 300 implementing the system 100, as shown in FIG. 1 to FIG. 2 for detection of the one or more objects in the event data, according to some embodiments herein. As depicted in FIG. 3, the computing environment 300 comprises at least one data processing unit 306 that is equipped with a control unit 302 and an Arithmetic Logic Unit (ALU) 304, a plurality of networking devices 308 and a plurality Input output, I / O devices 310, a memory 312, a storage 314. The data processing unit 306 may be responsible for implementing the system 100 and method 600 described in FIGs. 1 to 3. For example, the data processing unit 306 in some embodiments be equivalent to the processing circuitry 102 of the system 100 as described above in reference to FIG. 2. The data processing unit 306 is capable of executing software instructions stored in memory 312. The data processing unit 306 receives commands from the control unit 302 in order to perform its processing. Further, any logical and arithmetic operations involved in the execution of the instructions are computed with the help of the ALU 304. The computer program is loadable into the data processing unit 306, which may, for example, be comprised in an electronic apparatus (such as the platform). When loaded into the data processing unit 306, the computer program may be stored in the memory 312 associated with or comprised in the data processing unit 306. According to some embodiments, the computer program may, when loaded into and run by the data processing unit 306, cause execution of method steps according to, for example, any of the methods illustrated in FIG. 2 as described herein.The overall computing environment 300 may be composed of multiple homogeneous and / or heterogeneous cores, multiple CPUs of different kinds, special media and other accelerators. Further, the plurality of data processing unit 306 may be located on a single chip or over multiple chips. The algorithm comprising of instructions and codes required for the implementation are stored in either the memory 312 or the storage 314 or both. At the time of execution, the instructions may be fetched from the corresponding memory 312 and / or storage 314 and executed by the data processing unit 306. In case of any hardware implementations various networking devices 308 or external I / O devices 310 may be connected to the computing environment to support the implementation through the networking devices 308 and the I / O devices 310.
Claims
1. A gaze communication system (100) for utilizing visually evoked potentials (VEPs) of a user for communication and cognitive rehabilitation, the system comprising: a sensing unit (102) configured to sense one or more electroencephalogram (EEG) signals associated with a user; a processor (104) coupled to the sensing unit (102), and the processor (104) configured to: filter and pre-process the one or more EEG signals by a signal processing moduleto remove noise and artifacts from EEG data associated with the one or more EEG signals; extract one or more features from the processed EEG signals, the one or more features are associated with visually evoked potentials (VEPs) of the user; classify and identify VEPs corresponding to at least one visual stimulus associated with the user, wherein the VEPs corresponding to the at least one visual stimulus is identified by way of classification of the plurality of features; and provide, by using a gaze-controlled communication device (110), a real-time feedback to the user based on the one or more identify VEPs, wherein the real-time feedback comprises a recommendation to the user to select letters,words, or phrases,displayed on a user interface (106) of the system, focusing gaze of the user on the at least one visual stimuli.
2. The gaze communication system (100) as claimed in claim 1, wherein the sensing unit (102) comprises EEG sensors, EmotivEpoc+, OpenBCI EEG Systems, Muse 2, or Muse S, or Integrated Multi-Bio-Signal Systems selected from Empatica E4, OpenBCI Systems, or Shimmer3.
3. The gaze communication system (100) as claimed in claim 1, wherein the user interface (106) coupled to the processor (104), and configured to display visual information such that the user generatesavisual stimulusin response to the visual information, wherein the visual information comprising one of, letters, words, and phrases, wherein the user, to facilitate gaze communication, selects at least one attribute of the visual information. \4. The gaze communication system (100) as claimed in claim 1, wherein the one or more features comprisesat least one of a P100, N75, and N145 components.
5. The gaze communication system (100) as claimed in claim 1, wherein the VEPs are classified using one or more machine learning techniques.
6. The gaze communication system (100) as claimed in claim 1, wherein the processor (104) is further configured to generate a prediction signal that facilitates to suggest the visual information to the user.
7. The gaze communication system (100) as claimed in claim 1, wherein the gaze-controlled communication devicecomprises a selection mechanism being triggered upon identifying the VEPs, whereinthe selection mechanism comprises the recommendation, and whereinupon selection of the recommendation, the gaze-controlled communication devicegenerates a feedback signal.
8. The gaze communication system (100) as claimed in claim 7, further comprising a feedback unit (108) coupled to the gaze-controlled communication device, and configured to generate one ofa visual feedback, a haptic feedback, and an audio feedback upon generation of the feedback signal.
9. A method (200) for utilizing visually evoked potentials (VEPs) of a user for communication and cognitive rehabilitation, the method (200) comprising: sensing (202), by a sensing unit (102), one or more electroencephalogram (EEG) signals associated with a user, wherein the sensing unit (102) comprises EEG sensors, EmotivEpoc+, OpenBCI EEG Systems, Muse 2, or Muse S, or Integrated Multi-Bio-Signal Systems selected from Empatica E4, OpenBCI Systems, or Shimmer3; filteringand pre-processing (204), by a processor (104) coupled to the sensing unit (102), the one or more EEG signals by a signal processing moduleto remove noise and artifacts from EEG data associated with the one or more EEG signals; extracting (206), by the processor (104), one or more features from the processed EEG signals, the one or more features are associated with visually evoked potentials (VEPs) of the user, wherein the one or more features comprisesat least one of a P100, N75, and N145 components; and classifying and identifying (208), by the processor (104),VEPs corresponding to at least one visual stimulus associated with the user, wherein the VEPs corresponding to the at least one visual stimulus is identified by way of classification of the plurality of features, wherein the VEPs are classified using one or more machine learning techniques; and providing (210), by the processor (104) and by using a gaze-controlled communication device (110), a real-time feedback to the user based on the one or more identify VEPs, wherein the real-time feedback comprises a recommendation to the user to select letters,words, or phrases,displayed on a user interface (106), focusing gaze of the user on the at least one visual stimuli, and wherein the gaze-controlled communication devicecomprises a selection mechanism being triggered upon identifying the VEPs, whereinthe selection mechanism comprises the recommendation, and whereinupon selection of the recommendation, the gaze-controlled communication device generates a feedback signal.
10. The method (200) as claimed in claim 8, further comprising: displaying, on a user interface (106) coupled to the processor (104), display visual information such that the user generatesa visual stimulus in response to the visual information, wherein the visual information comprising one of, letters, words, and phrases, wherein the user, to facilitate gaze communication, selects at least one attribute of the visual information; generating a prediction signal that facilitates to suggest the visual information to the user; and generating one ofa visual feedback, a haptic feedback, and an audio feedback upon generation of the feedback signal.
